{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/synthesizing-robust-adversarial-examples","title":"Synthesizing Robust Adversarial Examples","arxiv_id":"1707.07397","date":"2017-07-24","proceeding":null,"authors":["Anish Athalye","Logan Engstrom","Andrew Ilyas","Kevin Kwok"],"abstract":"Standard methods for generating adversarial examples for neural networks do\nnot consistently fool neural network classifiers in the physical world due to a\ncombination of viewpoint shifts, camera noise, and other natural\ntransformations, limiting their relevance to real-world systems. We demonstrate\nthe existence of robust 3D adversarial objects, and we present the first\nalgorithm for synthesizing examples that are adversarial over a chosen\ndistribution of transformations. We synthesize two-dimensional adversarial\nimages that are robust to noise, distortion, and affine transformation. We\napply our algorithm to complex three-dimensional objects, using 3D-printing to\nmanufacture the first physical adversarial objects. Our results demonstrate the\nexistence of 3D adversarial objects in the physical world.","url_abs":"http://arxiv.org/abs/1707.07397v3","url_pdf":"http://arxiv.org/pdf/1707.07397v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"synthesizing-robust-adversarial-examples","repo_url":"https://github.com/owenps/Adversarial_Generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"synthesizing-robust-adversarial-examples","repo_url":"https://github.com/adverML/synthesizing_robust_adversarial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"synthesizing-robust-adversarial-examples","repo_url":"https://github.com/prabhant/synthesizing-robust-adversarial-examples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.07397","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}